In a previous paper we have described a novel approach to coding verbatim responses to open-ended questions that relies on machine learning, and we have introduced VCS(TM), a working computerized system that we have designed and implemented according to this approach. In the present paper we present the results of a number of experiments we have run on several datasets of respondent data in order to assess the accuracy and the efficiency of VCS(TM).
Machines that learn how to code open-ended survey data. Part II: experiments on real respondent data
Esuli A;Fagni T;Sebastiani F
2009
Abstract
In a previous paper we have described a novel approach to coding verbatim responses to open-ended questions that relies on machine learning, and we have introduced VCS(TM), a working computerized system that we have designed and implemented according to this approach. In the present paper we present the results of a number of experiments we have run on several datasets of respondent data in order to assess the accuracy and the efficiency of VCS(TM).File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
prod_161100-doc_131389.pdf
accesso aperto
Descrizione: Machines that learn how to code open-ended survey data. Part II: experiments on real respondent data
Dimensione
202.28 kB
Formato
Adobe PDF
|
202.28 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
